Skip to main content
Glama
cliwant

mcp-sam-gov

by cliwant

nih_reporter_search_projects

Read-only

Search awarded NIH research grants by organization, state, and fiscal year. Retrieve project details including award amount and recipient UEI for SAM/USAspending linkage.

Instructions

Search awarded NIH RePORTER research-GRANT projects (keyless; api.reporter.nih.gov v2, POST/JSON — the FIRST non-GET getJson-port consumer) — the NEW federal research-funding recipient-enrichment axis (who receives NIH research money, by organization / state, joinable to SAM/USAspending via primary_uei). Structured, LIVE-CONFIRMED-narrowing criteria ONLY, AND-combined in a module-built body (NO raw passthrough): orgStates (UPPERCASE 2-letter USPS enum — the SSRF + silent-zero guard; a lowercase/unknown code silently returns zeros), orgNames (≤512 each, ≤20), fiscalYears (int array 1985..currentYear+1, ≤20), limit (1..500, def 50), offset (0..14,999, def 0). Returns { projects:[{ projectNum, projectTitle, fiscalYear, awardAmount, organization:{ name, state, primaryUei, primaryDuns, ueis, duns }, principalInvestigators, contactPiName, fundingIc }] } + honest _meta. HONESTY: (M2) records are RESEARCH GRANTS, NOT procurement contracts — primary_uei joins to SAM/USAspending recipients but the award nature differs (disclosed in every _meta.notes); totalAvailable = the EXACT meta.total (NEVER the page size, NEVER a lower bound); NIH caps keyless retrieval at the first 15,000 records (offset 0..14,999) — offset ≥ 15,000 ⇒ invalid_input, and past the window the count stays exact while records are UNREACHABLE (disclosed in a note; nextOffset is never a dead-end). Disclose-not-refuse: an unscoped query still returns the first page + the exact total + a narrow-your-criteria note. agencyIcCodes is intentionally NOT a filter (NIH silently drops it — it would be a false 'applied'). Genuine-empty (total:0) ⇒ complete:true/total:0; an outage/5xx/timeout THROWS; a 400 (bad offset/limit/type) ⇒ invalid_input; a 200 body that isn't {meta,results} or a non-numeric meta.total ⇒ schema_drift (never a fake empty). awardAmount is number|null (a real $0 award is 0, an absent amount is null).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoProjects per page (upstream hard cap 500), 1..500, default 50.
offsetNo0-based offset into the result set. HARD-CAPPED at 14,999: NIH caps keyless retrieval at the first 15,000 records (offset 0..14,999), so offset ≥ 15,000 is refused (invalid_input) — narrow criteria to reach records beyond the window. The count (totalAvailable) stays EXACT past the window.
orgNamesNoRecipient-organization name filter values (each ≤512 chars, max 20). LIVE-CONFIRMED to narrow. e.g. ['MASSACHUSETTS INSTITUTE OF TECHNOLOGY']. A value matching no org returns a genuine total:0.
orgStatesNoRecipient-organization US state/territory 2-letter USPS codes (UPPERCASE — the enum is the SSRF value guard + the silent-zero guard: a lowercase 'ca' or an unknown 'ZZ' silently returns zeros, so a typo is an invalid_input, never read as 'no NIH funding'). LIVE-CONFIRMED to narrow. e.g. ['CA','MA']. Max 20.
fiscalYearsNoNIH fiscal years to include (int array, 1985..2027, max 20). LIVE-CONFIRMED to narrow. e.g. [2023,2024].
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is extremely transparent beyond annotations. It details the POST method, error handling (invalid_input, schema_drift), caps, exact totals, and honesty about unreachable records. Annotations (readOnlyHint, openWorldHint) are simple, and the description adds significant behavioral context without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is verbose but well-structured, using sections, examples, and warnings. Every sentence adds value. It could be slightly shorter, but given the complexity (5 parameters, no output schema), the length is justified. It is not excessively wordy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is highly complete for a tool with no output schema. It describes the return structure, error conditions, and edge cases (empty results, outages, drift). Parameter count and complexity are high, but every aspect is covered, including honesty notes. No missing information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds substantial value beyond parameter names and types. It explains case sensitivity for orgStates, the cap and behavior for limit/offset, and live-conformation for all filters. This helps an agent understand proper usage and edge cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool searches awarded NIH RePORTER research-grant projects. It specifies the API and data nature, but does not explicitly contrast with sibling tools. However, the unique focus on NIH grants makes it distinct among the listed siblings, which are primarily USASpending and other federal tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides detailed usage guidelines, including constraints (offset cap, keyless retrieval), warnings about agencyIcCodes being omitted, and notes on data nature (grants vs contracts). It does not explicitly say when not to use this tool, but the limitations serve as implicit guidance. More explicit alternative references would improve it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cliwant/mcp-sam-gov'

If you have feedback or need assistance with the MCP directory API, please join our Discord server